INDEX

Explanations

terms related to IP addresses and networking

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"IP" or "IP*" (Internet Protocol related)

np_acts-logits-general · gemini-2.0-flash

IP followed by network terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-1.00

 themſelves

-0.87

Efq

-0.85

 الرياضيه

-0.84

 ſhall

-0.81

 himſelf

-0.81

 itſelf

-0.81

 raiſ

-0.79

uſ

-0.79

PYX

-0.77

POSITIVE LOGITS

IP

1.04

ip

0.95

ip

0.85

IP

0.85

Ip

0.79

Ip

0.77

IPs

0.64

Lip

0.63

ips

0.58

ips

0.57

Activations Density 0.132%

terms related to IP addresses and networking

"IP" or "IP*" (Internet Protocol related)

IP followed by network terms

No Comments

No Known Activations